4 papers
Concept Subspaces Compute Beyond the Logit Lens: A Weights-Only Test for Locating Representations Upstream of Readout
Aojie Yuan, Zhiyuan Julian Su, Haiyue Zhang +1
A concept subspace's effect on model behavior does not establish how it relates to the output readout. We introduce a two-sided geometric diagnostic that measures an extracted subs…
Jacobian Rank Collapse in Decision-Focused Learning
Aojie Yuan, Haiyue Zhang, Zijian Su
Decision-focused learning (DFL) trains predictors through downstream objectives, but a different loss need not provide an independent parameter-update direction. We characterize th…
Unfolding Scientific Papers into Multi-Turn Generation Trajectories for Continued Pre-Training
Qiankai Xu, Qiguang Chen, Zixin Su +4
A recent line of synthetic-data work reconstructs the thinking behind existing text rather than rewriting the text itself, but it operates on short web passages, recovers only loca…
SEVA: Self-Evolving Verification Agent with Process Reward for Fact Attribution
Aojie Yuan, Yi Nian, Haiyue Zhang +2
Hallucination is the reliability bottleneck for LLM-based agents, and fact attribution verifiers are the last line of defense -- yet today's verifiers emit only opaque binary label…